Qwen3.6 35B A3B
Intelligence benchmarks
Artificial Analysis indexes - compared with the best open and proprietary models
Intelligence
43.5
AA Index
Coding
35.2
AA Index
Agentic
58.3
AA Index
Intelligence Index - Qwen3.6 35B A3B vs. the field
Best open-weight models (you can run locally) and leading proprietary models for context.
Coding Index comparison
Agentic Index comparison
Benchmark data from Artificial Analysis · updated 2026-06-07.
Standard benchmarks
Performance across standard evaluations
| Benchmark | Score |
|---|---|
| GPQA | 84.1 |
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve Qwen/Qwen3.6-35B-A3BNew to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Qwen3.6 35B A3B
Qwen3.6 35B A3B is a 36B-parameter apache-2.0 model from Alibaba. It scores 43.5 on the Artificial Analysis Intelligence Index (coding 35.2). At Q4_K_M it needs roughly 21 GB of VRAM, placing it in the 12-24gb hardware tier.
Specifications
| Spec | Value |
|---|---|
| Parameters | 36B |
| Context length | 262K tokens |
| License | apache-2.0 |
| Modalities | text, vision |
| Released | 2026-04-15 |
| Weights | Qwen/Qwen3.6-35B-A3B |
Benchmarks
Artificial Analysis Intelligence Index - Qwen3.6 35B A3B vs. leading closed models:
| Model | Intelligence | Coding | GPQA |
|---|---|---|---|
| Qwen3.6 35B A3B | 43.5 | 35.2 | 84.1 |
| GPT-5.5 (xhigh) | 60.2 | 59.1 | 93.5 |
| Claude Opus 4.8 (max) | 61.4 | 56.7 | 92 |
| Gemini 3.1 Pro Preview | 57.2 | 55.5 | 94.1 |
| Grok 4.3 (high) | 53.2 | 41 | 90.1 |
Source: Artificial Analysis (2026-06-04).
VRAM requirements
| Quant | VRAM | Runs on |
|---|---|---|
| Q4_K_M | ~21 GB | RTX 3090, RTX 4090 |
| Q5_K_M | ~26 GB | RTX 6000 Ada, dual RTX 3090 |
| Q8_0 | ~39 GB | RTX 6000 Ada, dual RTX 3090 |
| FP16 | ~72 GB | A100 80GB, H100 |
VRAM is estimated from parameter count; MoE models still need all weights resident.
How to run
vLLM:
vllm serve Qwen/Qwen3.6-35B-A3BPopularity
Qwen3.6 35B A3B has 5,942,049 downloads in the last month on HuggingFace and 2,003 likes.
Frequently asked
Quick answers to common questions
How much VRAM does Qwen3.6 35B A3B need?
Qwen3.6 35B A3B with 36B parameters needs approximately 21 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Qwen3.6 35B A3B better than other Qwen models?
Qwen3.6 35B A3B has 36B parameters with 262,144 context - a strong choice for general use.
What license is Qwen3.6 35B A3B under?
Qwen3.6 35B A3B is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Qwen3.6 35B A3B well?
With 36B parameters, Qwen3.6 35B A3B requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Qwen3.6 35B A3B?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~26 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Qwen3.6 35B A3B's context window handle?
Qwen3.6 35B A3B supports a 262,144-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Qwen3.6 35B A3B?
Qwen3.6 35B A3B competes with other 18B–54B. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec
Similar by size
Comments coming soon
Configure NEXT_PUBLIC_GISCUS_REPO_ID and NEXT_PUBLIC_GISCUS_CATEGORY_ID at giscus.app to enable.